nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ik_llama_opt/src
History
Nexes the Elder 170467e835
Llama-quantize: Partial requant feature (#1313) 
* Partial Requant feature for llama-quantize

- Inspired by the recently portcopied --dry-run feature.
- Allows to partially requantize a split quantized .gguf by requantizing only the missing splits in the destination directory.
- Works both for GGUF which are split tensors by tensors, or by group of several tensors (though this one is not very much tested beyond 2 tensors by split).
- Vibe coded.

* Create output directory if it doesn't exist in llama-quantize

* Create output directory if it doesn't exist in gguf-split

* Add exit when directory fails to be created on Windows

* Use std::filesystem

* cleanup
 		2026-02-25 07:25:15 +01:00
..
CMakeLists.txt Factor out delta net (#1286) 2026-02-18 17:16:17 +01:00
llama-arch.cpp Fix llm_arch_is_hybrid (#1305) 2026-02-23 08:55:53 +01:00
llama-arch.h Qwen3.5-MoE: fix regenerating message error (#1295) 2026-02-21 18:24:12 +01:00
llama-build-context.cpp Slightly better graph parallel for Qwen3-Next (#1307) 2026-02-24 15:22:30 +01:00
llama-build-context.h Graph parallel for Qwen3-Next (#1292) 2026-02-23 07:58:00 +01:00
llama-context.h Add MTP decoding support for GLM-4.x MoE (#1270) 2026-02-22 18:14:39 +01:00
llama-cparams.h Add MTP decoding support for GLM-4.x MoE (#1270) 2026-02-22 18:14:39 +01:00
llama-delta-net.cpp Minor delta-net tweak (#1308) 2026-02-24 15:22:57 +01:00
llama-delta-net.h Factor out delta net (#1286) 2026-02-18 17:16:17 +01:00
llama-grammar.cpp llama : add token matching support to llama-grammar (#1220) 2026-02-03 07:57:17 +02:00
llama-grammar.h llama : add token matching support to llama-grammar (#1220) 2026-02-03 07:57:17 +02:00
llama-hparams.cpp Add MTP decoding support for GLM-4.x MoE (#1270) 2026-02-22 18:14:39 +01:00
llama-hparams.h WIP: Qwen3Next (#1266) 2026-02-16 06:50:28 +01:00
llama-impl.h server: stop processing the prompt when client disconnects (#1134) 2026-01-13 07:56:59 +02:00
llama-load-tensors.cpp Graph parallel for Qwen3-Next (#1292) 2026-02-23 07:58:00 +01:00
llama-mmap.cpp Enable CUDA graphs for MoE models + GPT-OSS support (#689) 2025-08-15 09:18:07 +03:00
llama-mmap.h Enable CUDA graphs for MoE models + GPT-OSS support (#689) 2025-08-15 09:18:07 +03:00
llama-model-loader.cpp Be able to read uint32_t and bool arrays from GGUFs (#1252) 2026-02-07 19:20:15 +02:00
llama-model-loader.h Merge ffn_up and ffn_gate experts tensors (#1137) 2026-01-12 18:30:53 +02:00
llama-model.cpp Qwen3.5-MoE: fix regenerating message error (#1295) 2026-02-21 18:24:12 +01:00
llama-model.h Fix max nodes (again) (#1306) 2026-02-23 11:17:37 +01:00
llama-quantize.cpp Llama-quantize: Partial requant feature (#1313) 2026-02-25 07:25:15 +01:00
llama-sampling.cpp adaptive p: collect probability before logit bias (#1314) 2026-02-24 15:39:17 +01:00
llama-sampling.h adaptive p: collect probability before logit bias (#1314) 2026-02-24 15:39:17 +01:00
llama-vocab.cpp Qwen3.5-MoE support (#1288) 2026-02-21 08:33:06 +01:00
llama-vocab.h Qwen3.5-MoE support (#1288) 2026-02-21 08:33:06 +01:00
llama.cpp Llama-quantize: Partial requant feature (#1313) 2026-02-25 07:25:15 +01:00
unicode-data.cpp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
unicode-data.h Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
unicode.cpp Server: refactor and rename functions (#1151) 2026-01-18 08:16:57 +02:00
unicode.h Enable CUDA graphs for MoE models + GPT-OSS support (#689) 2025-08-15 09:18:07 +03:00